-
Notifications
You must be signed in to change notification settings - Fork 0
/
Popularmovie.py
77 lines (60 loc) · 1.9 KB
/
Popularmovie.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import requests
from bs4 import BeautifulSoup
import pandas as pd
from tabulate import tabulate
import pyttsx3
# Initialize the text-to-speech engine
engine = pyttsx3.init()
engine.setProperty('rate', 195)
engine.setProperty('volume', 1.5)
topics_url = 'https://www.imdb.com/chart/moviemeter/'
response = requests.get(topics_url)
if response.status_code != 200:
raise Exception(f"Failed to load page {response}")
# else:
# print("Page loaded successfully")
page_contents = response.text
soup = BeautifulSoup(page_contents, 'html.parser')
def extractor(classes, tag):
l = []
selection_class = classes
topic_title_tags = soup.find_all(tag, {'class': selection_class})
for i in topic_title_tags:
tmp = i.text.strip()
if tmp == "":
l.append("N/A")
else:
l.append(tmp)
return l
def title_column():
title_l = extractor("titleColumn", "td")
new_l = []
movie_name = []
year = []
for i in title_l:
l = i.split("\n")
n1 = l[0].rstrip()
n2 = l[1].lstrip()
movie_name.append(n1)
year.append(n2)
new_l.append(movie_name)
new_l.append(year)
return new_l
def imdb_column():
imdb_l = extractor("ratingColumn imdbRating", "td")
return imdb_l
def link():
base_link = "https://www.imdb.com"
selection_class = "titleColumn"
topic_title_tags = soup.find_all("td", {'class': selection_class})
link_l = []
for i in topic_title_tags:
link = i.find('a')['href']
link_l.append(base_link + link)
return link_l
dict = {'Title': title_column()[0], 'Year': title_column()[
1], 'IMDB Rating': imdb_column(), 'Link': link()}
df = pd.DataFrame(dict)
engine.say("Here is a list of popular movies on IMDB")
engine.runAndWait()
print(tabulate(df, headers='keys', tablefmt='psql'))